修改auc计算参数

aucCaculate.py

@@ -3,7 +3,9 @@ import pandas as pd
 from config import *
 
 if __name__ == "__main__":
-    test = pd.read_csv(DIRECTORY_PATH + "test.csv", header=None)
+    test = pd.read_csv(DIRECTORY_PATH + "test{0}.csv".format(TEST_DATE), header=None)
     test_label = test[0].apply(lambda x: x[0]).values
-    predict = pd.read_csv(DIRECTORY_PATH + "output.txt", header=None)[0].values
+    predict = pd.read_csv(DIRECTORY_PATH +
+                          "testset{0}_output_model_{1}-{2}_lr{3}_lambda{4}.txt".format(TEST_DATE,
+                            DATA_START_DATE,DATA_END_DATE,"0.03","0.002"), header=None)[0].values
     get_roc_curve(test_label, predict, "1")

local/testCases.py

@@ -3,28 +3,19 @@ import datetime
 import pickle
 
 if __name__ == '__main__':
-    data = pd.read_csv("../data/test-data/raw-exposure.csv")[["cid","device_id"]]
-    data["y"]=1
+    data = pd.read_csv("../data/test-data/raw-exposure.csv")[["cid", "device_id"]]
+    data["y"] = 1
     test_data = data.tail(5)
+
     ffm = FFMFormatPandas()
     data = ffm.fit_transform(data, y='y')
-    data.to_csv("ffm_data.csv",index=False)
-    with open("ffm.object","wb") as f:
-        pickle.dump(ffm,f)
-    with open("ffm.object","rb") as f:
+    data.to_csv("ffm_data.csv", index=False)
+
+    with open("ffm.object", "wb") as f:
+        pickle.dump(ffm, f)
+    with open("ffm.object", "rb") as f:
         ffm = pickle.load(f)
     result = ffm.transform(test_data)
     print(result)
-    data_1 = pd.read_csv("ffm_data.csv",header=None).tail(5)
+    data_1 = pd.read_csv("ffm_data.csv", header=None).tail(5)
     print(data_1)
-
-
-
-
-
-
-
-
-
-
-

processData.py

@@ -3,6 +3,7 @@ from prepareData import fetch_data
 from utils import FFMFormatPandas
 import pandas as pd
 from config import *
+import pickle
 
 exposure, click, click_device_id = fetch_data(
     start_date=DATA_START_DATE, end_date=DATA_END_DATE)
@@ -53,6 +54,9 @@ print("Start ffm transform")
 start = time.time()
 ffm_train = FFMFormatPandas()
 data = ffm_train.fit_transform(data, y='y')
+with open(DIRECTORY_PATH+"ffm_{0}_{1}.pkl".format(DATA_START_DATE,DATA_END_DATE), "wb") as f:
+    pickle.dump(ffm_train, f)
+
 print("done transform ffm")
 end = time.time()
 print("ffm转化数据耗时：")